{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V3IMIQKCQKSRTP3QFERZGG73ZV","short_pith_number":"pith:V3IMIQKC","schema_version":"1.0","canonical_sha256":"aed0c4414282a519bf702923931bfbcd5bd5879cad58b09eec0fc5ff37751b2d","source":{"kind":"arxiv","id":"2607.00958","version":1},"attestation_state":"computed","paper":{"title":"LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Chemeris, Ming Jin, Randall Balestriero","submitted_at":"2026-07-01T13:56:21Z","abstract_excerpt":"Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self-supervised learning often depends on view and augmentation choices that encode domain-specific invariances. We study how an SSL recipe behaves when its method-specific configuration is reused unchanged after the pretraining signal family changes, framing this as a fixed-recipe stress test rather than a comparison against optimally tuned methods. We introduce Latent Euclidean Next-Embedding Prediction Architecture (LeNEPA), a no-augmentation ne"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.00958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T13:56:21Z","cross_cats_sorted":[],"title_canon_sha256":"6ff82e520ddae26334b409fa7726397fc3a07ada7124e1dc725c2b8dff1fe92f","abstract_canon_sha256":"11adebbcb5a52fa0f8ef427fda65060c735f53ea1115367badb67fe7a890386c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:24.507365Z","signature_b64":"m/w4IpW44bgeU3nXmX/0v2I1K2ioVAabd/fLtTBIJ8dRt36yCTRBHZPY49uOOzwilq+Q0ntUevOcqp1fNOejCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aed0c4414282a519bf702923931bfbcd5bd5879cad58b09eec0fc5ff37751b2d","last_reissued_at":"2026-07-02T01:18:24.506962Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:24.506962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Chemeris, Ming Jin, Randall Balestriero","submitted_at":"2026-07-01T13:56:21Z","abstract_excerpt":"Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self-supervised learning often depends on view and augmentation choices that encode domain-specific invariances. We study how an SSL recipe behaves when its method-specific configuration is reused unchanged after the pretraining signal family changes, framing this as a fixed-recipe stress test rather than a comparison against optimally tuned methods. We introduce Latent Euclidean Next-Embedding Prediction Architecture (LeNEPA), a no-augmentation ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00958","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.00958/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.00958","created_at":"2026-07-02T01:18:24.507029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00958v1","created_at":"2026-07-02T01:18:24.507029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00958","created_at":"2026-07-02T01:18:24.507029+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3IMIQKCQKSR","created_at":"2026-07-02T01:18:24.507029+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3IMIQKCQKSRTP3Q","created_at":"2026-07-02T01:18:24.507029+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3IMIQKC","created_at":"2026-07-02T01:18:24.507029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3IMIQKCQKSRTP3QFERZGG73ZV","json":"https://pith.science/pith/V3IMIQKCQKSRTP3QFERZGG73ZV.json","graph_json":"https://pith.science/api/pith-number/V3IMIQKCQKSRTP3QFERZGG73ZV/graph.json","events_json":"https://pith.science/api/pith-number/V3IMIQKCQKSRTP3QFERZGG73ZV/events.json","paper":"https://pith.science/paper/V3IMIQKC"},"agent_actions":{"view_html":"https://pith.science/pith/V3IMIQKCQKSRTP3QFERZGG73ZV","download_json":"https://pith.science/pith/V3IMIQKCQKSRTP3QFERZGG73ZV.json","view_paper":"https://pith.science/paper/V3IMIQKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00958&json=true","fetch_graph":"https://pith.science/api/pith-number/V3IMIQKCQKSRTP3QFERZGG73ZV/graph.json","fetch_events":"https://pith.science/api/pith-number/V3IMIQKCQKSRTP3QFERZGG73ZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3IMIQKCQKSRTP3QFERZGG73ZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3IMIQKCQKSRTP3QFERZGG73ZV/action/storage_attestation","attest_author":"https://pith.science/pith/V3IMIQKCQKSRTP3QFERZGG73ZV/action/author_attestation","sign_citation":"https://pith.science/pith/V3IMIQKCQKSRTP3QFERZGG73ZV/action/citation_signature","submit_replication":"https://pith.science/pith/V3IMIQKCQKSRTP3QFERZGG73ZV/action/replication_record"}},"created_at":"2026-07-02T01:18:24.507029+00:00","updated_at":"2026-07-02T01:18:24.507029+00:00"}